Artificial intelligence in ANESTHESIA .pdf

Artificial intelligence

1. Current Trends & Future Prospects
Dr. Tushar Chokshi
Vadodara
in Anaesthesia
Robot
Anesthetist
Tushar

2. •Audience Poll
•Introduction and Definition of AI
•History and Evolution of AI
•Stages and Types of AI
•How AI works and Uses of AI
•History of AI in Healthcare
•History of AI in Anesthesiology
•Current status of AI in Anesthesiology
•Future of AI in Anesthesiology
•Will AI replace Anesthesiologist
•Journal Articles of AI in Anesthesia
•Conclusion
•Take home message
•My Verdict
•Cartoons & Thanks
Outlines
Tushar

3. •DoyouknowyouarealreadyusingAIinyourpractice?
•HowwillAIaffectorchangeclinicaldecisionmakingin
Anaesthesiology?
•WillAIreduceerrorsinAnaesthesiapractice?
•WillyouacceptAIAnaesthesiapracticeinfuture?
•WillAIreplaceAnaesthesiologist?
Tushar

4. Which medical technologies and digital health
innovations can expect the brightest future in the next
decade of Anesthesiology ?
•Health Sensors and Telehealth
•Mixed Reality
•Surgical and Medical Robots
•Brain Computer Interfaces
•Nanotechnology
•5G
•Direct to Consumer Genetic Testing
•3D Printing
•Artificial Intelligence
•Quantum Computing
Tushar

5. Artificial intelligence is the capability of computers to
respond in a manner resembling human intelligence
Dictionary Definition
Human Computer

6. AI is like Electricity
Without electricity we can’t think this world Today
Like this
Without AI we won’t think this world in Future
53%
40%
Which Technologies use AI
Tushar

7. John McCarthy
In the 1956 they described
Artificial Intelligence
and gave the definition
Marvin Minsky
Fathers
of
AI
Tushar

8. An approachto make
computer, robot, or
product to think how
smart human think
To studiesof how
human brain thinks,
learns, decides and
works, when it tries to
solve problems
To improvecomputer
functions which are
related to human
knowledge, for
example, reasoning,
learning, and problem-
solving
The ultimateaim is
technological
singularitythe point at
which technology
overtakes the human
Tushar

9. AI
ML
DL
DS
Data Science
is a multi-disciplinary field
that usesscientificmethods,
processes, algorithms and
systems to extract knowledge
(It applies all mathematical
rules)
ArtificialIntelligence(AI),(JohnMcCarthy)
Isthecapabilityofcomputerstorespondina
mannerresemblinghumanintelligence(Machineto
thinkswithoutanyhumanintervention)examplesare
Drones,Selfdrivingcars,SearchengineslikeGoogle
andMedicaldiagnosiswithprocedurese.g.Robotsin
medicine
MachineLearning(ML),(ArthurSamuel)
Isasubsetofartificialintelligence(AI)that
providessystemstheabilitytoautomatically
learnandimprovefromexperiencewithout
beingexplicitlyprogrammed(Provides
statisticaltoolstoexploredata,sohere
machinelearnsautomaticallyfrompastdata
withoutanyconfusionofanyprogramme)
DeepLearning(DL),(AlexeyIvakhnenko)
Isasubsetofmachinelearningwhereartificialneural
networks,algorithmsinspiredbythehuman
brain,learnfromlargeamountsofdata(Human
brainthinking,alsocalledasDeepNeuralNetworkor
DeepNeuralLearning)
1956
1959
1965
Tushar

10. Artificial Intelligence
Machine Learning
Subset of AI
Deep Learning
Subset of ML
Data Science
All three
AI +ML+ DL
Basic Structure of Complete Artificial Intelligence
AI
ML
DLDS
Tushar

11. DATA
SCIENCE
of AI >> ML >> DL >> Data Science
2020’s2030’s
Tushar

12. Historyof AI
AI from 380 BC to 1900
Various mathematicians,
theologians, philosophers,
professors, and authors
mused about mechanical
techniques, calculating
machines, and numeral
systems
AI from 1900-1950
People took the “robot” idea
and implemented it into their
research, art, and discoveries
and in 1929 the first robot
was built in Japan
AI in the 1950s
Advances in the field of
artificial intelligence came.
Claude Shannon, “the father of
information theory,” published
“Programming a Computer for
Playing Chess. In 1956 John
McCarthy gave the official birth
of the word AI
AI in the 1960s
Innovation in the field of
artificial intelligence grew
rapidly through the 1960s.
Unimate, the first industrial
robot was developed to work
on a General
Motorsassembly
AI in the 1970s
gave way to accelerated
advancements, particularly
focusing on robots and
automatons. WABOT-1, the
first anthropomorphic robot,
was built in Japan at Waseda
University. Its features
included moveable limbs,
ability to see, and ability to
converse
AI in the 1980s
The rapid growth of artificial
intelligence continued
through the 1980s. Mercedes-
Benz built and released a
driverless van equipped with
cameras and sensors
AI in the 1990s
The end of the millennium has
helped artificial intelligence in its
continued stages of advance
growth. Deep Blue, a chess-playing
computer developed by IBM became
the first system to win a chess game
and match against a reigning world
champion Sony introduced AIBO
(Artificial Intelligence RoBOt), a
robotic pet dog
AI from 2000-2010
AI continued its trending
upward. Professor Cynthia
Breazeal developed Kismet, a
robot that could recognize
and simulate emotions with
its face. Honda releases
ASIMO,an artificially
intelligent humanoid robot
Tush
ar

13. 2010
Microsoft launched Kinect for
Xbox 360, the first gaming
device that tracked human
body movement using a 3D
camera and infrared detection
2011
Apple released Siri, a virtual
assistant on Apple iOS operating
systems. Siriuses a natural-
language user interface to infer,
observe, answer, and
recommend things to its human
user
2014
Microsoft released
Cortana, their version of a
virtual assistant similar to
Sirion iOS
2014
Amazon created Amazon
Alexa, a home assistant that
developed into smart speakers
that function as personal
assistants
2015
Elon Musk, Stephen Hawking,
and Steve Wozniak among
3,000 others started the
development and use of
autonomous weaponsfor
wars and autonomous cars
2015-2017
Google DeepMind’s Alpha Go,
a computer program that
plays the board gameGo,
defeated various (human)
champions
2016
Google released Google
Home,a smart speaker that
uses AI to act as a “personal
assistant” to help users
remember tasks, create
appointments, and search for
information by voice.
2017
The Face book Artificial
Intelligence Research lab
introduced chatbotsto
communicate with one
another
2018
Samsung introduced Bixby, a
virtual assistant. Bixby’s
functions includeVoice, where
the user can speak to and ask
questions, recommendations,
and suggestions
AI 2010 to Present Day
The last decade was
immensely important for AI
innovation
From 2010 onward, artificial
intelligence has become
embedded in our day-to-day
existence
In Smartphone having voice assistants
and computers that have
“intelligence” functions are everything
through advance AI
Tushar

14. Tushar
Landmark Years in
2011
Landmark Year of
AI in Anesthesiology

15. What to
expect for AI
in 2020
and beyond ?
Natural
language
processing
(NLP)
Machine
Learningand
Automated
Machine
Learning
Autonomous
vehicles
Chatbot+
Virtual
assistants
Tushar

16. ofAI
1)Artificial Narrow Intelligence (ANI)
Weak AI
-Machines has a narrow defined role of task
-e.g. SiRi, Alexa, Sophia, Self Driven Car
2)Artificial General Intelligence (AGI)
Strong AI
-Machine starts thinking just like humans
-under creation and developing all over world
3) Artificial Super Intelligence (ASI)
Super Strong AI
-Computers or Machines will surpass human beings
-Not exist and only seen in science fiction movies
Tushar

17. Reactive Machines AI
A basic type of AI system, they
can only react to currently
existing situations. e.g. Deep
Blue, a chess-playing
supercomputer created by IBM.
(So it works on preset data)
Limited Memory AI
Comprises of machine learning
models that derive knowledge
from previously-learned
information, stored data, or
events. e.g. Autonomous
vehicles, or self-driving cars.
(So it works on past data)
Theory of Mind AI
Is the decision-making ability equal
to the extent of a human mind, but
by machines. Two notable examples
are the robots Kismet and Sophia,
created in 2000 and 2016.
(So it works on emotional
intelligence)
Self-Awareness AI
Involves machines that have human-level
consciousness. This form of AI is not
currently in existence, but would be
considered the most advanced form of
artificial intelligence known to manand
(Pray to GOD it will not exist)
Four Types
of
Artificial
Intelligence
Tushar

18. How AI Works
Tushar
AI

19. Uses of AI
Medicine
Automobiles
Factories
Computers
Smartphone
Moles & Multiplex
Solar Energy
Electricity
Aeronautics
Roads & Highways
Robotics
Windmill
Air-Condition
Construction Metal Industries
Architect
Tushar

20. 800usesofAIarebeingbenchmarked,e.g.Assessing
breastcancerriskfromhistopathologicalimagery,
Guidinganti-venomselectionfromsnakeimages,and
Diagnosingskinlesions
2019
Variousspecialtiesinmedicinehaveshownanincreasein
researchregardingAIe.g.Radiology,Imaging,Disease
Diagnosis,Telehealth,Electronichealthrecords,Drug
Interactions,RoboticsurgeryandAnesthesiology
2010
AIprogramshavebeendevelopedandappliedtopracticessuch
asdiagnosisprocesses,treatmentprotocoldevelopment,drug
development,personalizedmedicine,andpatientmonitoringand
care
Beyond
1990
History of AI in Healthcare
First problem-solving program, orexpert system, known asDendraland
considered one of the most significant early uses of artificial intelligence
in medicine
1960-70
Brought the proliferation of the microcomputer and new levels of
network connectivity and applied to intelligent computing systems
in healthcare
1980-90

21. Uses of AI in Healthcare
Tushar

22. Tushar
Uses in Healthcare

23. Artificial Intelligence

24. Artificial Intelligence
In
Anesthesiology
Tushar

25. In historical development, anesthesia was the
earliest subject to implement artificial
intelligence
Anesthesiology first established the concept and
model of pharmacokinetics-pharmacodynamics of
clinical drugs PK/PD model (Pharmacological Robots)
In the 1980s, Servo anesthesia theory system
was formed, this was embryonic form of
automated anesthesia and robotic anesthesia
In 1990s, intravenous anesthesia Target-
Controlled drug Infusion (TCI) has been applied
in clinical practice
With the gradual improvement of anesthesia
monitoring, especially anesthesia depth EEG
monitoring system, the open-loop and closed-
loop automatic anesthesia system established
In recent years, anesthetic robots, technology
robots, diagnosis robots developed rapidly
History
Of AI in
Anaesthesiology

26. Since 2011
AI in anaesthesiology
is developing
tremendously

27. Current Status
of
AI in Anaesthesiology
(from 2011 to 2020)
Tushar

28. Two types Anaesthesia
Robotswere developed
1)ManualRobots
2)PharmacologicalRobots
The use of the Magellan
robot to perform
peripheral nerve blocks
Manual robots include the Kepler
Intubation System (KIS) intubating
robot, designed to utilized video
laryngoscopy and a robotic arm to
place an endotracheal tube
Pharmacological robots include the
McSleepy intravenous sedation
machine, designed to administer
propofol, narcotic, and muscle
relaxant
The use of the DaVinci
surgical robot to
perform regional
anesthetic blockade
The iControl-RP machine
closed-loop system
intravenous anesthetic
delivery system which makes
its own decisions regarding
the IV administration of
remifentanil and propofol
Tushar
2011
to
2020

29. Currently AI
involved in all
Anesthetizing
patient, who
requires
Preoperative
assessment of all
past medical
problems from the
history
The diagnosis
and treatment of
any complication
during or
following the
anesthetic
Physical examination
Laboratory evaluation
Mask ventilation of
an unconscious patient
Placement of an ET tube
Observation of all vital
monitors during surgery
Removal of the ET tube
at the conclusion of
most surgeries

30. From onwards
Anesthesia Practice
with AI will be
Tushar

31. AI in Pre Anaesthesia Checkups(PACs)
•Google Translate will be very useful in PAC
•We can talk and do PAC in patient’s mother tongue
language by AI interface
•e.g. English Speech ---> English Text --->Local text --->
Local Speech
SocommunicationwithpatientthroughAIintheir
languagewillbecomeroutineandalreadyestablished
Tushar

32. AI in Operation Theatres in Future
In future anaesthesiologist will command all gadgets,
monitors and lights in OT by AI which will be
connected with different AI systems
•Ok Google–Increase the height of OT table
•Alexa–Brighten and adjust the OT head lights
•Siri–Increase the AC cooling to 20 degree
Tushar
--Start the Music and adjust the voice

33. Contd.
•OurfutureAnaesthesiaworkstationwillbe
operatedbyAIwithjustvoicecommand&data
entry
•MonitorswillbecontrolledandselfcheckedbyAI
•SwitchOnandSwitchOffAnaesthesiawillbecome
realitythroughAIinnearfuture
And, some AI enabled functions are already in
some OT machines and monitors
Tushar

34. AI in Tele Anaesthesia
•WithAIyouwillbevirtuallypresentwithpatientand
colleagueanaesthesiologiststoguidethemintheirPeri
operativeperiodandinallprocedures
•EvenyoucancontrolallOTgadgetswithyourSmartphone
AIApps
•TeleanaesthesiaisnotanewconceptbutcombinedwithAI
itisveryusefulforteaching,inCMEsandConferences(e.g.
mywebinartalk)
•CombinedwithAugmentedReality(AR)andAIwillchange
theconceptofTeleAnaesthesia,andyouwillbegiving
virtualanaesthesiatodistantOTpatients(andit’sareality
e.g.TeleanaesthesiafromCanadatoItalybyDrHammerling
andcolleagues)
Tushar

35. In Future
from 2025Onwards
We
Tushar

36. Tushar
2025 Onwards

37. Augmented Reality
Tushar
AI healthcare Model in Future

38. AI Anaesthesiology
AI will work in Anaesthesiology as a Specialty
•Anaesthesiologistsneedagoodmixofcognitiveand
dexteritybasedlabour
•AIwillprimarilyresultintheautomationofcognitivework,
itmaybethatourhandspreventfullautomationofthe
specialty
•Thegeneraldexteritythathumanspossessallowsforawide
rangeoffunctionalinteractionwithourenvironment
•AsAI-basedautomationsystemsgainfurthercapability,they
maybeabletoperformsemiautonomousanesthesia
maintenance,wheretheAI-enabledmachinetakesover
specifieddomainsofanesthesiamaintenance
Tushar

39. Contd.
•Anaesthesiamightneverbefullyautomatedbecauseit
involvesdexterity-basedlabour
•Currentroboticdevicesdon'thaveexactdexterity
requiredfortasks
•However,AIcouldbeusedinanesthesiatodevelop
moreadvancedclinicaldecisionsupporttoolsbasedon
machinelearning
•Ultimately,AIandmachinelearningcouldenable
anesthesiatobecomeatrueperioperativemedicine
specialtyratherthanjustanintraoperativespecialty
•AIcouldassumesomeofanaesthesiologists'cognitive
workloadandsupport"arenewedemphasisonthe
doctor-patientrelationship,"
Tushar

40. Will AI reduce
Errors in Anesthesiology ?
•DependsonSafetyVs.Complexity(Complication)
•Humandexterity(skillhands)workswillnotbe
replacedbyAIAnaesthesiaorRoboticAnaesthesia
•AIcancontrolthegadgets,monitorsbut
anaesthesiologistwillrequireallthetimetodo
dexterityworksliketofillthesyringes,toputchest
electrodesortotakeclinicaldecisioninoddsituations
Tushar

41. But
that
Tushar

42. Will AI replace Anesthesiologist ?
ThereareclearlycognitivetasksthatAIwilleventuallyassume
fromhumananesthesiologists,butAIisnotabletodealwithmany
areasofdecisionmakingthatanesthesiologistsroutinelyperform
Likewhenthepatient‘swellbeingdeterioratesintheOT,almostall
surgeonswantananesthesiologistbeingtodiscusswhatitwilltake
togetthepatientstableagain.
Talkingtoarobotormachine(nomatterhowsmartitis)justisn’t
thesameasaddressingtheguywho’sbeendoinganesthesiafor
yourpatientsforlongtime
Tushar

43. >>IdonotthinkthatAIwillreplaceanaesthesiologistanytime
soon
>>Artificialintelligenceisstillattheverybeginningofprototyping,fixingandtestingall
errorsinanaesthesia
>>Ontheflipside,weshouldstartactivelyusingandtestingAIthatisavailableinorder
toexperienceitandlearntocorroborateitinouranaesthesiapractice
>>TheAIoftodaywillhelpanaesthesiologiststoskiptheboringstuffandhopefully
makethemmorefocusedandsmarter.Ifyouhaveatalentedteamandtheresourcesto
playwithintelligentmonitorsandanaesthesiamachines,youwillgetthebestresults
>>However,inthefuturewemightseeparticularrolesbeingreplaced.Thefirstpeople
tobeletgowilllikelybethoserolesthatareverytask-basedandlackcreativity
>>Thefutureofartificialintelligenceinanaesthesiaisunpredictable
>>WhatispredictableistheintentionforAIdevelopment.Fiveyearsfromnow,we
mightseeamazinggame-changinginventionsaswellascontinuoussteadyprogress
towardsmoreintelligent,self-thinkingmonitors,anaesthesiamachinesandTCIpumps
Tushar

44. Intelligent control in Anaesthesia
(super super speciality)
•Intelligentcontrolisanewandinterdisciplinarysubject
developedonmultipledirections,suchasartificial
intelligenceandautomaticcontrol
•In1967,LeondeandMendelfirstusedtheconceptof
"intelligentcontrol"toapplytechniquesofmemoryand
goaldecompositiontoimprovetheirabilitytodealwith
uncertainty
•Theintelligentcontrolsummarizedasthecombinationof
automaticcontrolandartificialintelligence
•ClosedloopTCIwithanaesthesiadepthmonitoris
intelligentcontrolsystem(AutoAnaesthesia)
•Itiswidelyusedinclinicalapplications,includingcardiac
surgery,pheochromocytomasurgery,gastrointestinal
surgeryandhashadgoodclinicalresults
Tushar

45. Intelligent control In Auto Anaesthesia
Tushar

46. Close Loop Anesthesia Delivery System
(CLADS)
Tushar
Determines Right Drug with Right Dose at Right Time by AI

47. Articles
from
Tushar

48. Pub Med Research
•Artificial Intelligence and Anesthesiology –833
•Computerized Analysis and Anesthesiology –282
•Machine Learning and Anesthesiology –337
•Deep Learning and Anesthesiology –157
•Smartphone in anaesthesia --134
More than 1700 articles in journals
( In Last 15 years)
Tushar

49. Artificial IntelligenceinAnesthesiology:
Current Techniques, Clinical Applications, and Limitations
Anesthesiology.2020 Feb;132(2):379-394. doi: 10.1097/ALN.0000000000002960.
Hashimoto DA,Witkowski E,Gao L,Meireles O,Rosman G.
Six themes of applications ofartificial
intelligenceinanesthesiology:
e.g.
(1) Depth of anesthesia monitoring,
(2) Control of anesthesia,
(3) Event and risk prediction,
(4) Ultrasound guidance,
(5) Pain management, and
(6) Operating room logistics
Based on papers identified in the review,
several topics withinartificial
intelligencewere described and
summarized:
(1)Machine learning (including supervised,
unsupervised, and reinforcement learning),
(2) Techniques inartificial intelligence(e.g.,
classical machine learning, neural networks and
deep learning, Bayesian methods),
(3) Major applied fields inartificial intelligence
Artificial intelligencehas the potential to impact the practice ofanesthesiologyin aspects
ranging from perioperative support to critical care delivery to outpatient pain management
CONCLUSIONS
https://www.ncbi.nlm.nih.gov/pubmed/31939856
Tushar

50. Recent advances in the technology of anesthesia
F1000Res v.9; 2020 PMC7236591, 2020 May
Christian Seger, Maxime Cannesson,
Thepracticeofanesthesiologyisinextricablydependentupontechnology
Consumertechnologyandtelemedicinehaveexplodedontothesceneofoutpatient
medicine,andperioperativemanagement
Preoperativeevaluationshavebeendoneviateleconference,withcopiousconsumer-
generatedhealthdata
Insidetheoperatingsuite,monitoringhasbecomelessinvasive,andclinicaldecision
supportsystemsarecommon
Automationloomslargeinthefutureofanesthesiologyasclosed-loopanesthesia
deliverysystemsarebeingtestedincombination
Automation in the delivery of anesthetics and artificial intelligence
Monitoring inside the operating rooms: advances in non-invasive monitoring
Monitoring beyond the operating room: telemedicine and wearable health-care technologies
Clinical decision support and anesthesia information management systems
The innovation landscape in anesthesiology technology
Conclusions

51. A Novel Artificial Intelligence System for Endotracheal Intubation
Prehosp Emerg Care.2016 Sep-Oct;20(5):667-71. doi: 10.3109/10903127.2016.1139220. Epub 2016 Mar 17.
Carlson JN,Das S,De la Torre F,Frisch A,Guyette FX,Hodgins JK,Yealy DM
CONCLUSIONS
Initial efforts at computer algorithms using artificial
intelligence are able to identify the glottic opening with over
80% accuracy. With further refinements, video laryngoscopy
has the potential to provide real-time, direction feedback to
the provider to help guide successful ETI
https://www.ncbi.nlm.nih.gov/pubmed/26986814
Tushar

52. Machine Learning Models of Post-Intubation Hypoxia During General Anesthesia
Stud Health Technol Inform 2017;243:212-216.
Sippl P,Ganslandt T ,Prokosch HU ,Muenster T ,Toddenroth D
CONCLUSIONS
https://www.ncbi.nlm.nih.gov/pubmed/28883203
We interpret that our machine learning models could be instrumental for
computerized observational studies of the clinical determinants of post-
intubation oxygen deficiency. Future research might also investigate
potential benefits of more advanced preprocessing approaches such as
automated feature learning
Tushar

53. Machine Learning Approach for Preoperative Anaesthetic Risk Prediction
Int. J. of Recent Trends in Engineering and Technology, Vol. 1, No. 2, Nov 2009
Karpagavalli S , Jamuna KS , and Vijaya MS
Riskisubiquitousinmedicinebutanesthesiaisanunusualspecialtyasitroutinely
involvesdeliberatelyplacingthepatientinasituationthatisintrinsicallyfullofrisk.
Patientsafetydependsonmanagementofthoserisks;consequently,anesthetisthas
beenattheforefrontofclinicalriskmanagement.Anaestheticriskclassificationisof
primeimportancenotonlyincarryingouttheday-to-dayanestheticpracticebut
coincideswithsurgicalrisksandmorbiditycondition.Thepreoperativeassessmentis
madetoidentifythepatientsrisklevelbasedonAmericanSocietyofAnesthesiologists
(ASA)scorethatiswidelyusedinanestheticpractice.Thishelpstheanesthetistto
maketimelyclinicaldecision.
In the research work, three supervised machine learning schemes were applied on the
preoperative assessment data to predict the anaesthetic risk of the patients and the
performance of the learning methods were evaluated based on their predictive
accuracy and ease of learning
CONCLUSIONS
Tushar

54. Conclusion
Our study demonstrated that the deep learning model is superior to traditional
PK–PD model in predicting BIS during Propofol and Remifentanil target-controlled
infusions in surgical patients. The major advantage of the deep learning approach
is its performance and extensibility. We expect that the accumulation of clinical
big data will make the deep learning model more powerful and extend its
application to a variety of clinical situations in the future.
Prediction of Bispectral Index during Target-controlled Infusion of
Propofol and Remifentanil: (A Deep Learning Approach)
Hyung-Chul Lee, M.D.;Ho-Geol Ryu, M.D., Ph.D.;Eun-Jin Chung, M.D.;Chul-Woo Jung, M.D., Ph.D.
ANESTHESIOLOGY : Perioperative Medicine|March 2018
https://anesthesiology.pubs.asahq.org/article.aspx?articleid=2656314
Tushar

55. Automated anesthesia carts reduce drug recording
errors in medication administrations -A single centre
study in the largest tertiary referral hospital in China
J Clin Anesth.2017 Aug;40:11-15. doi: 10.1016/j.jclinane.2017.03.051. Epub 2017 Apr 13.
Wang Y,Du Y,Zhao ,Ren Y,Zhang W.
CONCLUSIONS
The utilization of automated anesthesia carts reduced the
drug recording errors in medication administrations of
anesthesia
https://www.ncbi.nlm.nih.gov/pubmed/28625429
The total error rate was 7.3% with the automated anesthesia carts (1 in 14
administrations) and 11.9% with conventional manual carts (1 in 8 administrations)
Tushar

56. First robotic tracheal intubations in humans
using the Kepler intubation system (KIS)
BJA: British Journal of Anaesthesia, Volume 108, Issue 6, June 2012, Pages 1011–
1016,https://doi.org/10.1093/bja/aes034
T. M. Hemmerling R. Taddei M. WehbeC. ZaouterS. CyrJ. Morse
Conclusions
We present the first human testing of a robotic intubation system for oral
tracheal intubation. The success rate was high at 91%.Future studies are
needed to assess the performance and safety of such a systemBJA: British Journal of Anaesthesia, Volume 108, Issue 6, June 2012, Pages 1011–1016, https://doi.org/10.1093/bja/aes034
The content of this slide may be subject to copyright: please see the slide notes for details.
Fig1 Illustration of the KIS. The system consists of: a ThrustMaster
T.Flight Hotas X joystick (Guillemot Inc.), a ...
Tushar

57. Technical communication:
First robotic ultrasound-guided nerve blocks in humans using the Magellan system
Anesth Analg.2013 Feb;116(2):491-4. doi: 10.1213/ANE.0b013e3182713b49. Epub 2013 Jan 9.
Hemmerling TM,Taddei R,Wehbe M,Cyr S,Zaouter C,Morse J.
Ultrasound-guided nerve blocks are becoming a standard of modern anesthesia.
We developed a robotic system, Magellan, to perform nerve blocks using a
remote control center.
Wepresentthefirsthumantestingofaroboticultrasound-guidednerve
blocksystem.Thesuccessratewas100%.Thetotalperformancetimewas
approximately3minutesto4minutes
Conclusions
https://www.ncbi.nlm.nih.gov/pubmed/23302984
Tushar

58. McSleepy: Automated Anaesthesia System
"Wehavebeenworkingonclosed-loopsystems,wheredrugsareadministered,their
effectscontinuouslymonitored,andthedosesareadjustedaccordingly,forthelastfive
years,”saidDr.ThomasM.HemmerlingofMcGill’sDepartmentofAesthesiaandthe
MontrealGeneralHospital,whoheadsITAG(IntelligentTechnologyinAesthesiaresearch
group),ateamofanesthesiologists,biomedicalscientistsandengineers.
World's first totally automated
administration of an anaesthetic in May 2008
Tushar

59. Father of
Robotic Anesthesia
Tushar

60. Robotic Anesthesia –A Vision for the Future of Anesthesia
Transl Med UniSa, 2011 Sep-Dec; 1: 1–20. Published online 2011 Oct 17.
Thomas M Hemmerling, MSc, MD, DEAA,Riccardo Taddei, MD,
*
Mohamad Wehbe,
MSc,Joshua Morse,Shantale Cyr, PhD, andCedrick Zaouter, MD
*
It offers a first classification of robotic anesthesia by separating it into pharmacological
robots and robots for aiding or replacing manual gestures. Developments in closed loop
anesthesia. First attempts to perform manual tasks using robots
From airway control to anesthesia control
Pharmacologic Robots
Closed loop for hypnosis
Closed loop of Anaesthesia
Closed loop of Analgesia
Anesthesia robots to aid or replace manual gestures
Teleanesthesia
Regional anaesthesia procedure
Placing a perineural catheter for continuous nerve block
Robotic Intubation
Artificial intelligence
Tushar

61. Automated Assessment of Difficult Airway With Facial
Recognition Techniques (PeScho)
https://clinicaltrials.gov/ct2/show/NCT02022397
Responsible
Party:
Patrick Schoettker,MDPD, Associate Professor, University of Lausanne Hospitals
ClinicalTrials.gov
Identifier:
NCT02022397
Other Study ID
Numbers:
183/09
CTI ( Other Grant/Funding Number: Swiss Commission Technology and Innovation
12636.1 )
First Posted: December 27, 2013
Last Update
Posted:
September 26, 2019
Last Verified: September 2019
Study Type:Observational [Patient Registry]
EstimatedEnrolment:6000 participants
Observational Model:Cohort
Time Perspective:Prospective
Target Follow-Up
Duration:
1 Day
Official Title:Automatic Assessment of Difficult Ventilation and Intubation From Automatic Face Analysis
and Artificial Intelligence
Study Start Date:March 2012
EstimatedPrimary
Completion Date:
December 23, 2020
Study Completion Date:December 23, 2020
Tushar

62. Artificial Intelligence and Machine Learning in Anesthesiology
Christopher W. Connor, M.D., Ph.D
Anesthesiology12 2019, Vol.131, 1346-1359. doi:
https://doi.org/10.1097/ALN.0000000000002694
Advances in technology and monitoring can change the impetus for machine learning.
For example, a neural network developed to detect esophageal intubation from flow-
loop parameters and will be obviated by continuous capnography
Uses a very highly augmented data set in conjunction with logistic regression to produce
an algorithmic model that can, inpost hocanalysis, detect the incipient onset of
hypotension up to 15 min before hypotension actually occurs
Neural network approach to predicting the Bispectral Index (BIS) based upon the
infusion history of propofol and remifentanil
The most plausible route to the introduction of artificial intelligence and machine
learning into anesthetic practice is that the routine intraoperative management of
patients will begin to be handed off to closed-loop control algorithms
Tushar

63. EthiconEndo-Surgery,aJohnson&Johnson
subsidiary,createdSEDASYS,acomputer-assisted
devicethatadministerstheprescriptiondrug
propofolintothebloodstreamviaintravenousIV
infusion(approvedin2013)
Thedevicecandetectsignsassociatedwithover
sedationandcanautomaticallymodifyorstop
infusion
Butitwaswithdrawnfrommarket
SEDASYS
Tushar

64. Artificial intelligence, machine learning and the pediatric airway
Matava C, et al. Paediatr Anaesth. 2019.
Artificialintelligenceandmachinelearningarerapidlyexpandingfields
withincreasingrelevanceinanesthesiaand,inparticular,airway
management.Theabilityofartificialintelligenceandmachinelearning
algorithmstorecognizepatternsfromlargevolumesofcomplexdata
makesthemattractiveforuseinpediatricanesthesiaairwaymanagement
Theycriticallyassessthecurrentevidenceontheuseofartificial
intelligenceandmachinelearningintheassessment,diagnosis,
monitoring,procedureassistance,andpredictingoutcomesduring
pediatricairwaymanagement
Tushar

65. The Feasibility of a Completely Automated Total IV
Anesthesia Drug Delivery System for Cardiac Surgery
Anesth Analg 2016;123:885–93
Cedrick Zaouter, MD, MSc, Thomas M. Hemmerling, MD, Romain Lanchon, MD,
Emanuela Valoti, MD, Alain Remy, MD, Sébastien Leuillet, MSc, and Alexandre Ouattara, MD, PhD
Inthispilotstudy,wetestedanovelautomaticanesthesiasystemforclosedloop
administrationofIVanesthesiadrugsforcardiacsurgicalprocedureswith
cardiopulmonarybypass.Thisanesthesiadrugdeliveryrobotintegratesall3components
ofgeneralanesthesia:hypnosis,analgesia,andmusclerelaxation
CONCLUSIONS:
Thecompletelyautomatedclosed-loopsystemtestedinthisinvestigation
couldbeusedsuccessfullyandsafelyforcardiacsurgerynecessitating
cardiopulmonarybypass.Theresultsofthepresenttrialshowedsatisfactory
clinicalperformanceofanesthesiacontrol
Tushar

66. 67
Existing AI enabled Monitors and Anaesthesia Work Station ( Very Complex )
Tushar

67. Tushar

68. Today’s Robotic and Artificial Intelligence Theatre
Tushar

69. In2030
AI will replace this type
of complex anaesthesia monitors and machine
into
Tushar

70. Tushar

71. AI
Monitor
In 2030
Switch On
&
Switch Off
Anaesthesia
Machine
Tushar
Future AI Anaesthesia Work Station

72. Robotic Anaesthesia

73. Will BE ACCURATE
Tushar
With AI
Will go away
And

74. Applications ofartificial intelligence(AI) and machine learning (ML) have
shown promising results in anesthesiology
It is clear thatAIwill find many applications inanesthesiacare, in
delivering real-time results
The contributions of AI to general anesthesia have got advancements in
monitors, TCI machines & closed-loop systems
The fields of postoperative pain management and chronic pain have also
benefited from AI by developing software
AI will also increase the training power of simulations thereby improving
education in anesthesiology
Much more work is required to understand exactly the scope, that AI
will play in anesthesiology
But, in general AIwill certainly continue enhancing the patient
experience andAnesthesiologist expertise
A
B
C
D
E
F
G

75. Artificial intelligence(AI) inanesthesia is theuseof complex
algorithms and softwaretoestimate human cognition
It will never replace Anaesthesiologist
AI or Robot will be Pilot, but we will always be
there as Co-Pilot
AI will definitely reduce the errors in
anaesthesia practice
In near future we all will witness the changes of
anaesthesia practice with AI
AI in anaesthesia will put zero complication rate
in our practice, which we never recognised
Ultimately we have to accept artificial intelligence in our
practice which we are already practicing
1)
2)
3)
4)
5)
6)
7)

76. The potential of Artificial Intelligence in
anesthesiology with changing patient’s lives beyond
recognition is both exciting and challenging
The anaesthesiologist has to accept the use of AI in
their future practice for learning the art of modern
AI enabled Anaesthesia Machines, Monitors and
Gadgets
Tushar

77. 2030
2025
Tushar

78. This will be Reality in Future
Tushar

79. BLOCKS
Artificial Intelligence Under Litigation
Tushar

80. In Future
Anesthesiologist will be the assistant of AI Robots
Tushar

81. Finally We have to accept Robots and AI
Will be Our Pilots & Teachers in our practice
Tushar

82. AI means
Artificial Intelligence
but
AI means
Anesthetist Intelligence
also

83. Join
Face Book Groups of
“TIVA Society of India”
&
“Indian Society for Opioid Free Anesthesia”
[email protected]
https://sites.google.com/site/tusharchokshisite
9825062245/9979319721

84. Tushar